validate_motion

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden, and it does not state whether the tool is read-only, whether it mutates the authored clips, what it returns, or how errors are surfaced. 'Audit' implies a non-destructive read, but that is inference, not disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tight sentence with the detection scope front-loaded and no filler. The terseness is efficient rather than padded, though it errs toward under-specification given the zero param coverage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-param validation tool with no annotations, no output schema, and 0% schema coverage, the description omits the return shape, error format, and the role of runtime_json. An agent knows what it detects but not enough to call it confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three parameters, so the description is the only source of meaning. It loosely echoes 'clips' and 'handoff' from the parameter list, but the required runtime_json (presumably the bulk of the payload) is entirely unexplained, as are the expected shapes of clips and handoffs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Audit') and resource ('authored clips') and enumerates the error classes checked (frame-grid, curve, handoff, loop-seam), which tells an agent exactly what the tool detects. It never distinguishes itself from siblings like validate_output, audit_preview, or spine_doctor, which sound like overlapping validation tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to reach for this tool versus validate_output or audit_preview, and no prerequisites or exclusions. The agent must infer the trigger condition from the sibling name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.